Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 11794
    Prev
    Next
    INDEX
    Explanations

    gerunds and words ending in 'ing', particularly in the context of actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bindet
    -0.72
    ArgsConstructor
    -0.68
    InstanceState
    -0.67
    apollo
    -0.64
     IgE
    -0.63
    égard
    -0.62
    gól
    -0.62
    setopt
    -0.61
     thorax
    -0.59
    icef
    -0.59
    POSITIVE LOGITS
    ting
    1.20
    ating
    1.19
    ging
    1.10
    izing
    1.04
    GGGG
    1.00
    zing
    1.00
    cting
    1.00
    TING
    0.97
    cing
    0.97
    gggg
    0.95
    Activations Density 1.048%

    No Known Activations